Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that define foundational concepts or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tail
    -0.20
    ish
    -0.19
    oit
    -0.19
    лев
    -0.17
    esi
    -0.17
    irsch
    -0.17
    aise
    -0.16
    outs
    -0.16
    alim
    -0.15
    sdale
    -0.15
    POSITIVE LOGITS
    ëŀ
    0.17
    most
    0.16
    conds
    0.16
    dır
    0.16
    глÑıд
    0.15
    curity
    0.15
    paring
    0.15
    nut
    0.15
    croll
    0.15
    yal
    0.15
    Act Density 0.022%

    No Known Activations